Design of an Intelligent Variable-Flow Recirculating Aquaculture System Based on Machine Learning Methods

doi:10.3390/app11146546

IOCAS-IR > 实验海洋生物学重点实验室

	Design of an Intelligent Variable-Flow Recirculating Aquaculture System Based on Machine Learning Methods
	Chen, Fudi1,2,3 ; Du, Yishuai 1,2,3; Qiu, Tianlong1,2,3 ; Xu, Zhe 4; Zhou, Li 1,2,3; Xu, Jianping 1,2,3; Sun, Ming 1,2,3,5; Li, Ye1,2,3 ; Sun, Jianming 1,2,3,4,5
	2021-07-01
发表期刊	APPLIED SCIENCES-BASEL
卷号	11 期号:14 页码:15
通讯作者	Sun, Jianming(jianming_sun@outlook.com)
摘要	Featured Application The proposed classification models could be adapted to develop a recirculating aquaculture system with continuous variable-flow control technology. A recirculating aquaculture system (RAS) can reduce water and land requirements for intensive aquaculture production. However, a traditional RAS uses a fixed circulation flow rate for water treatment. In general, the water in an RAS is highly turbid only when the animals are fed and when they excrete. Therefore, RAS water quality regulation technology based on process control is proposed in this paper. The intelligent variable-flow RAS was designed based on the circulating pump-drum filter linkage working model. Machine learning methods were introduced to develop the intelligent regulation model to maintain a clean and stable water environment. Results showed that the long short-term memory network performed with the highest accuracy (training set 100%, test set 96.84%) and F1-score (training 100%, test 93.83%) among artificial neural networks. Optimization methods including grid search, cuckoo search, linear squares, and gene algorithm were proposed to improve the classification ability of support vector machine models. Results showed that all support vector machine models passed cross-validation and could meet accuracy standards. In summary, the gene algorithm support vector machine model (accuracy: training 100%, test 98.95%; F1-score: training 100%, test 99.17%) is suitable as an optimal variable-flow regulation model for an intelligent variable-flow RAS.
关键词	recirculating aquaculture system variable-flow regulation model circulating pump-drum filter linkage working technique machine learning methods gene algorithm support vector machine
DOI	10.3390/app11146546
收录类别	SCI
语种	英语
资助项目	Key Program for International Cooperation on Scientific and Technological Innovation, Ministry of Science and Technology of the People's Republic of China[2017YFE0118300] ; National Key R&D Programs of China[2019YFD0900800] ; National Key R&D Programs of China[2019YFD0900502]
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
WOS类目	Chemistry, Multidisciplinary ; Engineering, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS记录号	WOS:000675940200001
出版者	MDPI
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/175786
专题	实验海洋生物学重点实验室
通讯作者	Sun, Jianming
作者单位	1.Chinese Acad Sci, Ctr Ocean Megasci, Inst Oceanol, CAS, Qingdao 266071, Peoples R China 2.Chinese Acad Sci, Ctr Ocean Megasci, Inst Oceanol, Shandong Prov Key Lab Expt Marine Biol, Qingdao 266071, Peoples R China 3.Qingdao Natl Lab Marine Sci & Technol, Lab Marine Biol & Biotechnol, Qingdao 266071, Peoples R China 4.Dalian Huixin Titanium Equipment Dev Co Ltd, Dalian 116039, Peoples R China 5.Liaoning Ocean & Fisheries Sci Res Inst, Liaoning Prov Key Lab Marine Biol Resources & Eco, Dalian Key Lab Conservat Fishery Resources, Dalian 116023, Peoples R China
第一作者单位	中国科学院海洋大科学研究中心
通讯作者单位	中国科学院海洋大科学研究中心
推荐引用方式 GB/T 7714	Chen, Fudi,Du, Yishuai,Qiu, Tianlong,et al. Design of an Intelligent Variable-Flow Recirculating Aquaculture System Based on Machine Learning Methods[J]. APPLIED SCIENCES-BASEL,2021,11(14):15.
APA	Chen, Fudi.,Du, Yishuai.,Qiu, Tianlong.,Xu, Zhe.,Zhou, Li.,...&Sun, Jianming.(2021).Design of an Intelligent Variable-Flow Recirculating Aquaculture System Based on Machine Learning Methods.APPLIED SCIENCES-BASEL,11(14),15.
MLA	Chen, Fudi,et al."Design of an Intelligent Variable-Flow Recirculating Aquaculture System Based on Machine Learning Methods".APPLIED SCIENCES-BASEL 11.14(2021):15.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
applsci-11-06546.pdf（5140KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览